Azure Databricks Import a Notebook and Run It

arazzo: 1.0.1
info:
  title: Azure Databricks Import a Notebook and Run It
  summary: Import a notebook, confirm it landed, then submit a run of it.
  description: >-
    Deploys notebook source into the workspace and immediately executes it.
    The workflow imports base64-encoded notebook content to a workspace path,
    confirms the object exists with a status check, submits a one-time run of
    the imported notebook, and polls the run until its life cycle state is
    TERMINATED. Every step spells out its request inline so the flow can be read
    and executed without opening the underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: azureDatabricksApi
  url: ../openapi/azure-databricks-openapi.yml
  type: openapi
workflows:
- workflowId: import-notebook-and-run
  summary: Import a notebook into the workspace, confirm it, and run it.
  description: >-
    Imports notebook content, verifies it with getWorkspaceObjectStatus,
    submits a one-time run, then polls getJobRun until TERMINATED.
  inputs:
    type: object
    required:
    - token
    - notebookPath
    - content
    - language
    - taskKey
    - existingClusterId
    properties:
      token:
        type: string
        description: Databricks personal access token for the Authorization header.
      notebookPath:
        type: string
        description: Absolute workspace path to import the notebook to.
      content:
        type: string
        description: Base64-encoded notebook source content (max 10 MB).
      language:
        type: string
        description: Notebook language, one of SCALA, PYTHON, SQL, or R.
      taskKey:
        type: string
        description: Unique key identifying the single task in the run.
      existingClusterId:
        type: string
        description: Id of an existing cluster to run the imported notebook on.
  steps:
  - stepId: importNotebook
    description: >-
      Import the base64-encoded notebook content to the target path in SOURCE
      format, overwriting any existing object.
    operationId: importWorkspaceObject
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    requestBody:
      contentType: application/json
      payload:
        path: $inputs.notebookPath
        format: SOURCE
        language: $inputs.language
        content: $inputs.content
        overwrite: true
    successCriteria:
    - condition: $statusCode == 200
  - stepId: confirmImport
    description: >-
      Confirm the imported object exists at the path and is a NOTEBOOK before
      attempting to run it.
    operationId: getWorkspaceObjectStatus
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    - name: path
      in: query
      value: $inputs.notebookPath
    successCriteria:
    - condition: $statusCode == 200
    - condition: $response.body#/object_type == "NOTEBOOK"
    outputs:
      objectId: $response.body#/object_id
      objectType: $response.body#/object_type
  - stepId: submitRun
    description: >-
      Submit a one-time run of the imported notebook on the existing cluster
      and capture the run_id.
    operationId: submitRun
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    requestBody:
      contentType: application/json
      payload:
        run_name: import-and-run
        tasks:
        - task_key: $inputs.taskKey
          existing_cluster_id: $inputs.existingClusterId
          notebook_task:
            notebook_path: $inputs.notebookPath
            source: WORKSPACE
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      runId: $response.body#/run_id
  - stepId: pollRun
    description: >-
      Retrieve the run state. Repeat until the run life_cycle_state is
      TERMINATED, then end with the final result_state.
    operationId: getJobRun
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    - name: run_id
      in: query
      value: $steps.submitRun.outputs.runId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      lifeCycleState: $response.body#/state/life_cycle_state
      resultState: $response.body#/state/result_state
    onSuccess:
    - name: finished
      type: end
      criteria:
      - context: $response.body
        condition: $.state.life_cycle_state == "TERMINATED" || $.state.life_cycle_state == "INTERNAL_ERROR"
        type: jsonpath
    - name: stillRunning
      type: goto
      stepId: pollRun
      criteria:
      - context: $response.body
        condition: $.state.life_cycle_state == "PENDING" || $.state.life_cycle_state == "RUNNING" || $.state.life_cycle_state == "TERMINATING"
        type: jsonpath
  outputs:
    notebookPath: $inputs.notebookPath
    objectId: $steps.confirmImport.outputs.objectId
    runId: $steps.submitRun.outputs.runId
    resultState: $steps.pollRun.outputs.resultState